© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12906
    Prev
    Next
    INDEX
    Explanations

    special characters followed by code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irmi
    -0.07
    ucch
    -0.07
     ['$
    -0.07
    azza
    -0.07
    è½¼
    -0.07
    (None
    -0.07
    =?,
    -0.07
    ashtra
    -0.07
    å¤ļå°ijéĴ±
    -0.07
    åĬ¡å·¥
    -0.07
    POSITIVE LOGITS
    äºĨä¸ĢèĪ¬
    0.07
    翼
    0.07
    */)
    0.07
    INCREMENT
    0.07
    æļĹé»ij
    0.07
    å«
    0.06
    éĻ£
    0.06
    æ¡ĪåĨħ
    0.06
    åģ´
    0.06
    ÃĵS
    0.06
    Activations Density 0.100%

    No Known Activations